Complete digital access to quality FT journalism with expert analysis from industry leaders. Pay a year upfront and save 20%.
南方周末：决赛第三天结束时，现场一直等到欧洲时间次日凌晨两点多才公布结果。那五个多小时的等待过程中，你都在做些什么？
。关于这个话题，新收录的资料提供了深入分析
$ time nix eval --expr 'builtins.foldl'\'' (acc: _: acc + 1) 0 (builtins.genList (x: x) 1000000)'
The setup was modest. Two RTX 4090s in my basement ML rig, running quantised models through ExLlamaV2 to squeeze 72-billion parameter models into consumer VRAM. The beauty of this method is that you don’t need to train anything. You just need to run inference. And inference on quantized models is something consumer GPUs handle surprisingly well. If a model fits in VRAM, I found my 4090’s were often ballpark-equivalent to H100s.